Quick Start - Inya Docs

Prerequisites

Before you begin, ensure you have:

Valid API credentials (API Key and User ID)
cURL installed, or a tool like Postman for making HTTP requests

Speech-to-Text (STT)
Text-to-Speech (TTS)

REST
WebSocket

You’ll need an audio file for testing (WAV, MP3, FLAC, or other common formats); duration ≤ 30 seconds, mono/stereo.

Your First Speech-to-Text Call

Minimal example to transcribe a Hindi audio file:

curl --X POST https://api.vachana.ai/stt/v3 \
  --H 'Content-Type: multipart/form-data' \
  --H 'X-API-Key-ID: <x-api-key>' \
  --H 'X-API-Request-ID: <x-api-request-id>' \
  --F audio_file='/path/to/your/audio.wav' \
  --F language_code=hi-IN

Replace these values:

<x-api-key>: Your Vachana API key
<x-api-request-id>: Your Vachana request ID
/path/to/your/audio.wav: Path to your audio file
hi-IN: Language code (see Language Codes for all options)

Expected STT Response

On success, you’ll receive a JSON response like:

{
  "success": true,
  "request_id": "req_abc123",
  "transcript": "नमस्ते, आप कैसे हैं?"
}

For real-time, low-latency transcription of streaming audio, Vachana provides a WebSocket API.

Connection

Connect using a WebSocket client with the required authentication headers:

const ws = new WebSocket("wss://api.vachana.ai/stt/v3", {
  headers: {
    "x-api-key-id": "<your-api-key>",
    "x-api-request-id": "<your-api-request-id>"
  }
});

Request Payload

WebSocket frames must be raw binary PCM audio exactly 1024 bytes (512 samples × 16-bit) per chunk (16kHz, mono). No JSON wrapper is used for client-to-server messages.

Expected STT Response

The server will respond with JSON text frames containing transcription segments:

{
  "type": "transcript",
  "timestamp": "2024-01-15T10:30:05.987Z",
  "text": "Hello, how are you today?",
  "audio_duration_ms": 2340,
  "segment_id": "seg_abc123",
  "segment_index": 1,
  "latency": 320,
  "detected_language": "en"
}

REST
Streaming (SSE)
WebSocket

You’ll need text to synthesize and a desired voice/language.

Your First Text-to-Speech Call

Minimal example for REST TTS (synchronous audio). This endpoint returns binary audio representing the full synthesized response.

curl --X POST https://api.vachana.ai/api/v1/tts/inference \
  --H 'Content-Type: application/json' \
  --H 'X-API-Key-ID: <x-api-key>' \
  --H 'X-API-Request-ID: <x-api-request-id>' \
  --d '{
        "text": "नमस्ते, आप कैसे हैं?",
        "voice": "Sia",
        "model": "vachana-voice-v1",
        "audio_config": {
          "sample_rate": 44100,
          "num_channels": 1,
          "sample_width": 2,
          "encoding": "linear_pcm",
          "container": "wav"
        }
      }' \
  --output response.wav

Expected TTS Response

A successful request will return a 200 OK HTTP status. The response body will contain raw binary audio data representing the synthesized text, adhering to the format specified in your audio_config.

HTTP/1.1 200 OK
Content-Type: audio/wav

<binary auto data>

Server-Sent Events (SSE) allows you to submit a TTS request via standard HTTP POST and progressively stream the synthesized audio back to the client as it’s generated.

Your First Streaming Call

curl --X POST https://api.vachana.ai/api/v1/tts/sse \
  --H 'Content-Type: application/json' \
  --H 'X-API-Key-ID: <x-api-key>' \
  --H 'X-API-Request-ID: <x-api-request-id>' \
  --d '{
        "text": "नमस्ते, आप कैसे हैं?",
        "voice": "Sia",
        "model": "vachana-voice-v1"
      }'

Expected SSE Response

A successful request will return a 200 OK HTTP status. The response body will contain a stream of server-sent events. Each chunk contains base64 encoded audio fragments.

HTTP/1.1 200 OK
Content-Type: text/event-stream

event: audio_chunk
data: UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAEAfAAABAAgAZGF0YQAAAAA=

event: audio_chunk
data: //NkxAAAAANIAAAAAExBTUUzLjEwMKqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq

event: completed
data: {"status": "success"}

For the lowest possible latency in interactive applications, use the WebSocket API to incrementally stream text in and pull continuous audio out.

Connection

Connect using a WebSocket client with the required authentication headers:

const ws = new WebSocket("wss://api.vachana.ai/api/v1/tts", {
  headers: {
    "x-api-key-id": "<your-api-key>",
    "x-api-request-id": "<your-api-request-id>"
  }
});

Request Payload

Once connected, send a JSON payload containing exactly what you want to synthesize.

{
  "text": "नमस्ते, आप कैसे हैं?",
  "voice": "Sia",
  "model": "vachana-voice-v1"
}

Expected TTS Response

Upon successful connection, the server will return a 101 Switching Protocols status to establish the WebSocket.Once the text payload is sent, the server will immediately begin streaming audio back as a sequence of binary WebSocket frames containing the raw PCM audio data, terminating or keeping the connection open depending on the application context.

Authentication Setup

The Vachana API uses header-based authentication with the same credentials for both STT and TTS.

Obtaining Credentials

API key provisioning is currently handled by our team to ensure personalized onboarding and support. To request your credentials: Send an email to speechstack@gnani.ai with the following details:

Use Case (optional): Brief description of your intended application (e.g. STT, TTS, or both)

What happens next:

Our team will generate your API credentials (api-key and user-id)
You’ll receive a ready-to-use cURL command with your credentials embedded
We’ll assign free credits to your account so you can start testing immediately — no payment required
You can begin using STT and/or TTS right away with the provided examples

Expected turnaround: API credentials are typically provisioned within 1 business day. No Credit Card Required: All new accounts receive complimentary credits for testing and evaluation.

Next Steps

Speech-to-Text: STT REST and STT WebSocket for all STT parameters and language options
Text-to-Speech: REST, Streaming (SSE), and WebSocket for TTS options

Vachana

Speech-to-Text

Text-to-Speech

​Prerequisites

​Your First Speech-to-Text Call

​Expected STT Response

​Connection

​Request Payload

​Expected STT Response

​Your First Text-to-Speech Call

​Expected TTS Response

​Your First Streaming Call

​Expected SSE Response

​Connection

​Request Payload

​Expected TTS Response

​Authentication Setup

​Obtaining Credentials

​Next Steps

Prerequisites

Your First Speech-to-Text Call

Expected STT Response

Connection

Request Payload

Expected STT Response

Your First Text-to-Speech Call

Expected TTS Response

Your First Streaming Call

Expected SSE Response

Connection

Request Payload

Expected TTS Response

Authentication Setup

Obtaining Credentials

Next Steps